Back to Catalog

Build Multi-Agent Santa Quiz Game w/ Granite, CrewAI, Gradio

BeginnerGuided Project

Build your own multi-agent Santa Quiz Game with IBM Granite, CrewAI, and Gradio. Learn to orchestrate specialized agents with CrewAI agents and tasks to collaboratively research global traditions and generate interactive challenges. Use IBM Granite models to power high-quality text generation and secure environment variables for reliable system configuration. Integrate custom JavaScript snow effects and festive CSS styling to deliver a polished, immersive web interface. Explore how CrewAI enables agent collaboration and state-based logic to create a fully automated holiday experience.

Language

  • English

Topic

  • Artificial Intelligence

Skills You Will Learn

  • Artificial Intelligence, Multi-Agent System, CrewAI, LLM, Python, Gradio

Offered By

  • IBMSkillsNetwork

Estimated Effort

  • 45 mins

Platform

  • SkillsNetwork

Last Update

  • December 24, 2025
About this Guided Project
Have you ever wanted to bring a little extra magic to your holiday gatherings? While trivia games are a staple of festive parties, creating one that is both historically accurate and entertaining can be a challenge. In this project, you will build an AI-powered Christmas Trivia Host that brings global traditions to life. By orchestrating a team of specialized CrewAI agents and integrating IBM watsonx.ai foundation models, you will create an interactive game that doesn't just recycle common facts, but also uncovers obscure folklore, generates witty multiple-choice challenges, and even simulates a judgment from Santa Claus himself. This system demonstrates the power of agentic workflows, where distinct AI personalities collaborate to research, format, and present information in a dynamic, user-friendly web application.



What You'll Learn

By the end of this project, you will be able to:
  • Orchestrate Multi-Agent Systems with CrewAI: Define and manage specialized agents, a Folklore Historian, an Entertainment Elf, and a Santa Judge, to handle distinct parts of a complex workflow.
  • Integrate Enterprise-Grade LLMs: Connect your application to IBM watsonx.ai to leverage the Granite model series for high-quality, context-aware text generation.
  • Implement Secure Configuration Patterns: Master the use of os.environ to safely manage API keys and project credentials, a critical skill for deploying secure AI applications.
  • Design Interactive Web UIs with Gradio: Build a polished frontend featuring custom HTML/CSS styling and JavaScript animations (like falling snow) to create an immersive user experience.
  • Manage Application State Logic: Learn how to use state machines within a web app to handle multi-turn conversations, ensuring smooth transitions between question generation and answer evaluation.
  • Deploy and Share: Package your Python code into a shareable web demo that can be accessed by friends, family, or potential employers.


Who Should Enroll

  • Python Developers looking to expand their skills into Generative AI and agent orchestration.
  • AI Enthusiasts curious about how frameworks like CrewAI can simplify the creation of complex, multi-step AI behaviors.
  • Educators and Gamification Designers interested in using AI to create dynamic, educational content on the fly.
  • Creative Coders who want to learn how to blend backend logic with frontend aesthetics for thematic applications.


Why Enroll

This project bridges the gap between backend AI engineering and frontend user experience design. Instead of a simple text-in/text-out chatbot, you will build a system with personality and structure. You will move beyond basic prompting to designing a collaborative AI team that follows strict formatting rules and persona guidelines. By the end, you will have a working holiday trivia game, practical experience with state-of-the-art agent frameworks, and a template for building any kind of interactive, educational AI assistant.


What You'll Need

To get the most out of this project, you should have:
  • Basic Python programming knowledge.
  • Familiarity with the concept of APIs (helpful but not required).
  • Interest in Generative AI, Game Design, and Web Development.
All dependencies are pre-configured in the environment, and the project runs best on current versions of Chrome, Edge, Firefox, or Safari.

Instructors

Jianping Ye

Data Scientist Intern at IBM

I'm Jianping Ye, currently a Data Scientist Intern at IBM and a PhD candidate at the University of Maryland. I specialize in designing AI solutions that bridge the gap between research and real-world application. With hands-on experience in developing and deploying machine learning models, I also enjoy mentoring and teaching others to unlock the full potential of AI in their work.

Read more

Contributors

Matthew Wu

Marketer at IBM

Supporting Cognitive Class and IBM through digital marketing and tailored content creation

Read more

Abdul Fatir

Data Scientist

Abdul specializes in Data Science, Machine Learning, and AI. He has deep expertise in understanding how the latest technologies work, and their applications. Feel free to contact him with questions about this project or any other AI/ML topics.

Read more